|
{ |
|
"best_metric": 1.02787184715271, |
|
"best_model_checkpoint": "./outputs/checkpoint-500", |
|
"epoch": 0.6666666666666666, |
|
"eval_steps": 100, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9997, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.0932432413101196, |
|
"eval_runtime": 721.0711, |
|
"eval_samples_per_second": 2.677, |
|
"eval_steps_per_second": 0.336, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.897, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.0685845613479614, |
|
"eval_runtime": 721.8083, |
|
"eval_samples_per_second": 2.674, |
|
"eval_steps_per_second": 0.335, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8812, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.0530365705490112, |
|
"eval_runtime": 727.1346, |
|
"eval_samples_per_second": 2.654, |
|
"eval_steps_per_second": 0.333, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8694, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.0397064685821533, |
|
"eval_runtime": 725.2926, |
|
"eval_samples_per_second": 2.661, |
|
"eval_steps_per_second": 0.334, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8549, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.02787184715271, |
|
"eval_runtime": 726.5869, |
|
"eval_samples_per_second": 2.656, |
|
"eval_steps_per_second": 0.333, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 2250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 1.2948397906255872e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|